重庆理工大学学报2025，Vol.39Issue(9)：229-237,9.DOI:10.3969/j.issn.1674-8425(z).2025.05.028
改进黑翅鸢算法优化神经网络的室内定位
Research on indoor localization of neural network optimized by improved black-winged kite algorithm
摘要
Abstract
Traditional path loss model of wireless signal is susceptible to multipath effect when predicting distance value,which leads to the decline of positioning accuracy in complex indoor environment.To address the issue,an indoor localization algorithm based on improved black-winged kite algorithm(IBKA)optimized back propagation neural network is proposed.Tent chaotic map,lens imaging reverse learning strategy and golden sine-strategy are introduced to optimize the Black Winged Kite algorithm.The benchmark test functions are compared to verify that IBKA delivers superior performances.Then IBKA optimizes the initial weights and thresholds of the neural network algorithm to build the IBKA-BP neural network ranging model.The RSSI signal sample data are collected and analyzed.Results show the root mean square error of IBKA-BP optimization algorithm is 21.42 cm,which is 63.25 cm,47.04 cm,33.77 cm and 28.78 cm lower than that of PLM,GWO-BP,BKA-BP and ISSA-BP.Moreover,the convergence speed is faster.Therefore,the proposed algorithm performs better in positioning in complex indoor environments.关键词
改进黑翅鸢算法/BP神经网络/RSSI测距算法/路径损耗模型Key words
IBKA/BP neural network/RSSI ranging algorithm/path loss model分类
天文与地球科学引用本文复制引用
杨晶晶,万里宏,张雪明,麦鴚,雷俊杰..改进黑翅鸢算法优化神经网络的室内定位[J].重庆理工大学学报,2025,39(9):229-237,9.基金项目
国家自然科学基金项目(62363018) （62363018）
企业委托技术开发项目(HZ2024K0114A) （HZ2024K0114A）
